Results 31 to 40 of about 6,652,811 (287)
Structured Graph Learning for Scalable Subspace Clustering: From Single View to Multiview [PDF]
IEEE Transactions on Cybernetics, 2021 Graph-based subspace clustering methods have exhibited promising performance. However, they still suffer some of these drawbacks: they encounter the expensive time overhead, they fail to explore the explicit clusters, and cannot generalize to unseen data
Zhao Kang +3 more
semanticscholar +1 more source
Adaptive Graph Representation for Clustering
IEEE Access, 2022 Many graph construction methods for clustering cannot consider both local and global data structures in the construction of initial graph. Meanwhile, redundant features or even outliers and data with important characteristics are addressed equally in the
Mei Chen +5 more
doaj +1 more source
Learning causality with graphs
AI Magazine, 2022 AbstractRecent years have witnessed a rocketing growth of machine learning methods on graph data, especially those powered by effective neural networks. Despite their success in different real‐world scenarios, the majority of these methods on graphs only focus on predictive or descriptive tasks, but lack consideration of causality. Causal inference can
Jing Ma, Jundong Li
openaire +2 more sources
Remote Sensing, 2022 Hyperspectral image classification (HSIC) methods usually require more training samples for better classification performance. However, a large number of labeled samples are difficult to obtain because it is cost- and time-consuming to label an HSI in a ...
Chunhui Zhao +3 more
doaj +1 more source
FedGTA: Topology-aware Averaging for Federated Graph Learning [PDF]
Proceedings of the VLDB Endowment, 2023 Federated Graph Learning (FGL) is a distributed machine learning paradigm that enables collaborative training on large-scale subgraphs across multiple local systems.
Xunkai Li +5 more
semanticscholar +1 more source
Preventing Failures by Dataset Shift Detection in Safety-Critical Graph Applications
Frontiers in Artificial Intelligence, 2021 Dataset shift refers to the problem where the input data distribution may change over time (e.g., between training and test stages). Since this can be a critical bottleneck in several safety-critical applications such as healthcare, drug-discovery, etc.,
Hoseung Song +2 more
doaj +1 more source
Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation [PDF]
International Conference on Machine Learning, 2023 Spatial-temporal graph learning has emerged as a promising solution for modeling structured spatial-temporal data and learning region representations for various urban sensing tasks such as crime forecasting and traffic flow prediction.
Qianru Zhang +5 more
semanticscholar +1 more source
Robust Graph Neural Networks via Ensemble Learning
Mathematics, 2022 Graph neural networks (GNNs) have demonstrated a remarkable ability in the task of semi-supervised node classification. However, most existing GNNs suffer from the nonrobustness issues, which poses a great challenge for applying GNNs into sensitive ...
Qi Lin +6 more
doaj +1 more source
Efficient Multi-View Clustering via Unified and Discrete Bipartite Graph Learning [PDF]
IEEE Transactions on Neural Networks and Learning Systems, 2022 Although previous graph-based multi-view clustering (MVC) algorithms have gained significant progress, most of them are still faced with three limitations. First, they often suffer from high computational complexity, which restricts their applications in
Siwei Fang +5 more
semanticscholar +1 more source
Learning Heat Diffusion Graphs [PDF]
IEEE Transactions on Signal and Information Processing over Networks, 2017 Effective information analysis generally boils down to properly identifying the structure or geometry of the data, which is often represented by a graph. In some applications, this structure may be partly determined by design constraints or pre-determined sensing arrangements, like in road transportation networks for example.
Thanou, D +3 more
openaire +3 more sources